research-grants

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/research-grants/SKILL.md

Quality

Content

62%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured with strong progressive disclosure—real reference and asset files are clearly signaled one level deep—and a clear phased workflow. Weaknesses are mild verbosity from restating broadly known agency context and guidance that is more descriptive than executable inline.

Suggestions

Trim or move agency mission/background restatements into the per-agency reference files, keeping SKILL.md focused on action guidance Claude would not already infer.

Add an explicit validation/checkpoint step to each workflow phase (e.g., 'Confirm page limits and required sections are met before advancing') to strengthen feedback loops.

Inline one or two short executable snippets or concrete worked examples (e.g., a Specific Aims scaffold) rather than only pointing to reference files.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-organized into scannable sections, but several passages restate widely known context (e.g., defining what each agency is, restating mission statements, generic 'grants are persuasive documents' framing) that could be trimmed for a Claude that already knows the domain.	3 / 5
Actionability	It offers concrete structure (page limits, section lists, phase activities/outputs) and one executable command for figure generation, but most guidance is descriptive rather than copy-paste ready; detailed how-to is delegated to reference files rather than shown inline.	3 / 5
Workflow Clarity	The five-phase workflow is clearly sequenced with explicit activities and outputs per phase and a concrete timing recommendation (submit 24-48 hours early); however, validation/verification checkpoints within phases are mostly implicit rather than explicit pass/fail gates.	4 / 5
Progressive Disclosure	The SKILL.md serves as a clear overview with well-signaled one-level-deep references (references/core_components.md, review_criteria.md, writing_principles.md, etc.) that all resolve to real files, plus a separate assets/ directory for templates; navigation is easy and content is appropriately split.	5 / 5
	Total	15 / 20 Passed

Description

62%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, agency-rich, and highly distinctive, clearly conveying what the skill does. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps the completeness dimension.

Suggestions

Add an explicit trigger clause such as 'Use when writing or revising research grant proposals, or when the user mentions NSF, NIH, DOE, DARPA, or NSTC submissions.'

Include common synonyms like 'grant application', 'funding proposal', or 'R01/solicitation' to broaden natural-language trigger coverage.

Consider naming a couple more concrete deliverables (e.g., biosketches, timelines, data management plans) to round out capability coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, compliance) and names five specific agencies, with only minor coverage gaps (e.g., biosketches/timelines not named).	4 / 5
Completeness	The 'what' is clearly and comprehensively stated, but there is no 'Use when...' or equivalent explicit trigger clause; the judging guidelines cap completeness at 3 when explicit trigger guidance is missing.	3 / 5
Trigger Term Quality	Includes strong natural terms users say (research proposals, budget preparation, broader impacts, significance statements, review criteria) plus agency acronyms, but lacks some synonyms like 'grant application' or 'funding proposal' and file/format extensions are not applicable.	4 / 5
Distinctiveness Conflict Risk	The niche is clearly defined by named federal agencies and proposal-specific tasks, with minimal overlap risk against generic writing or document skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/research-grants/SKILL.md
Commit: 49c6e97

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.